What's changed
- Bug fixes and reliability improvements
Claude Code
Developer ToolsAnthropic's agentic coding tool for the terminal, IDE and web.
Changelog
Added
- Added Claude Opus 5 (claude-opus-5) as the new default Opus model with 1M context and fast mode at $10/$50 per Mtok
- Added sandbox.network.strictAllowlist setting to deny non-allowlisted hosts for sandboxed commands without prompting
- Added DirectoryAdded hook that fires after /add-dir or SDK register_repo_root control request registers a new working directory mid-session
- Added mcp_server_errors to the headless stream-json init event, listing --mcp-config entries skipped by config validation
- Added workflowSizeGuideline settings key so the Dynamic workflow size guideline can be set from any settings file
- Added nested subagent forwarding in stream-json so subagents spawned at depth-2+ appear when --forward-subagent-text is set
- Added HTTP status and error text to claude mcp list and /mcp when a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace
- Added structured failure categories to self-hosted runner spawn and session failures to distinguish hook errors, runner crashes, and config errors
- Added the current default workflow size to the running-workflow status line with a pointer to /config for changing it
Changed
- Changed dynamic workflows to default to a medium size guideline aiming for fewer than 15 agents
- Changed managed MCP allowlist/denylist ${VAR} entries to resolve from the startup environment and managed-settings env instead of settings-file env
- Changed the /model picker to highlight only the newest model's name so the highlight marks the new release
- Updated the claude-api skill to default to Claude Opus 5 with a migration path from Opus 4.8
- Subagents can now spawn nested subagents up to depth 3 by default (was 1)
Fixed
- Fixed claude -p text output dropping the answer already produced when a turn dies on a mid-stream API error
- Fixed a permission you approved while a self-hosted runner was restarting being dropped when the session resumed
- Fixed the Fable model row showing Requires usage credits for plans that include it when a stale cache had baked the label in
- Fixed a SIGTERM arriving while a self-hosted runner was starting up leaving a stale active row until the lease expired
- Fixed the /model picker showing the merged Opus row as plain Opus instead of Opus (1M context)
- Fixed copy-on-select inside GNU screen printing base64 into the terminal instead of copying the selection
- Fixed Remote Control clients keeping a stale fast-mode status after a model switch, reconnect, or failed org check
- Fixed CLAUDE_CODE_GIT_BASH_PATH on Windows exiting or being used as bash when the path isn't a bash/sh binary
- Fixed Vim mode so pressing ← on an empty prompt returns to the agent view from NORMAL mode
- Fixed screen-reader mode rewriting the entire input line on every keystroke instead of echoing only the typed character
Removed
- Removed Opus 4.7 from fast mode; /fast now applies to Opus 5 and Opus 4.8
What's changed
- Added Claude Opus 5 (
claude-opus-5), now the default Opus model — 1M context, fast mode at $10/$50 per Mtok - Added
sandbox.network.strictAllowlistsetting to deny non-allowlisted hosts for sandboxed commands without prompting - Added
DirectoryAddedhook that fires after/add-diror the SDKregister_repo_rootcontrol request registers a new working directory mid-session - Added
mcp_server_errorsto the headless stream-json init event, listing--mcp-configentries skipped by config validation; terminal runs print a startup warning - Added the
workflowSizeGuidelinesettings key so the advisory Dynamic workflow size guideline can be set from any settings file; the/configrow is hidden while one does - Added nested subagent forwarding in stream-json: subagents spawned at depth-2+ now appear when
--forward-subagent-textis set, keyed by their spawning Agenttool_useid - Fixed
claude -ptext output dropping the answer already produced when a turn dies on a mid-stream API error - Added HTTP status and error text to
claude mcp listand/mcpwhen a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace - Fixed a permission you approved while a self-hosted runner was restarting being dropped when the session resumed, so the approved action now runs
- Fixed the Fable model row showing "Requires usage credits" for plans that include it, when a stale cache had baked the label in
- Fixed a SIGTERM arriving while a self-hosted runner was starting up leaving a stale active row until the lease expired; it now deregisters cleanly
- Added structured failure categories to self-hosted runner spawn and session failures, so hook errors, runner crashes and config errors can be told apart
- Fixed the
/modelpicker showing the merged Opus row as plain "Opus" instead of "Opus (1M context)" - Fixed copy-on-select inside GNU screen printing base64 into the terminal instead of copying the selection
- Fixed Remote Control clients keeping a stale fast-mode status after a model switch, reconnect, or failed org check
- Fixed
CLAUDE_CODE_GIT_BASH_PATHon Windows exiting or being used as bash when the path isn't a bash/sh binary; it's now ignored with a warning - Fixed Vim mode: pressing ← on an empty prompt now returns to the agent view from NORMAL mode, not just INSERT
- Fixed screen-reader mode rewriting the entire input line on every keystroke instead of echoing only the typed character
- Improved the "Remote Control is only available via api.anthropic.com" error to name the specific setting that caused it
- Improved
claude --teleportto show which repo your current checkout points at when it doesn't match the session's repo - Changed dynamic workflows to default to a medium size guideline (aim for fewer than 15 agents); pick another size or unrestricted with Dynamic workflow size in
/config - Changed managed MCP allowlist/denylist
${VAR}entries to resolve from the startup environment and managed-settings env instead of settings-file env - Changed the
/modelpicker to highlight only the newest model's name, so the highlight marks the new release rather than an arbitrary subset of the list - Added the current default workflow size to the running-workflow status line, with a pointer to
/configfor changing it - Removed Opus 4.7 from fast mode;
/fastnow applies to Opus 5 and Opus 4.8 - Updated the claude-api skill to default to Claude Opus 5, with a migration path from Opus 4.8
- Subagents can now spawn nested subagents up to depth 3 by default (was 1); set CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH=1 to disable nesting
Added
- Added screen-reader announcements of deleted text for word and line deletions in `--ax-screen-reader` mode
- Added HTTP status and error text to `claude mcp list` and `/mcp` when a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace
Changed
- Changed `/code-review` to run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target
Fixed
- Fixed Windows paths with `\u`-prefixed segments being corrupted into CJK characters in tool inputs
- Fixed the left arrow key discarding the conversation with no undo by adding confirmation prompts and Esc key support
- Fixed multi-line paste collapsing into one line with `j` in place of newlines in terminals that encode pasted newlines as Ctrl+J
- Fixed `/context` reporting stale pre-compact token usage after compacting from the message picker
- Fixed `/ultrareview` failing on descriptive arguments by allowing them to run a review of the current branch with the text applied as a note
- Fixed `/code-review ultra` silently running a local review in non-interactive sessions by launching the cloud review instead
- Fixed gateway spend metering to price Bedrock application-inference-profile ARNs and other config-mapped upstream model IDs at the configured model's rates
- Fixed mojibake when a long IDE selection was truncated mid-emoji and a case where a tool executor error could be silently dropped
- Fixed an engine teardown race that could start and abandon a phantom turn, and made input pushed after close consistently rejected
- Fixed spurious "[Request interrupted by user]" messages after interrupted tool calls and an unpaired `tool_use` block left in the transcript when a tool aborted mid-response
- Fixed VoiceOver reading "new line" instead of echoing the typed space at the end of the input in `--ax-screen-reader` mode
- Fixed plugin and settings panels not moving the terminal cursor to the focused row for screen reader and magnifier navigation
- Fixed crashes when a deeply nested watched directory tree was deleted or moved, and when rendering deeply nested UI trees
- Fixed pull request events occasionally being lost when a session exited immediately after creating or linking a PR
- Fixed the Bedrock setup wizard failing profile verification for assume-role profiles in partitioned AWS regions and on proxy-only networks
- Fixed rare negative or incorrect turn duration measurements after a system clock adjustment by timing turns with a monotonic clock
- Fixed the "N MCP servers need authentication" startup notice over-counting claude.ai connectors that aren't connected
What's changed
- Changed
/code-reviewto run as a background subagent, so review work no longer fills your conversation and keeps stacked slash commands as its review target - Added screen-reader announcements of deleted text for word and line deletions (
Option+Delete,Ctrl+W,Cmd+Backspace,Ctrl+U,Ctrl+K) in--ax-screen-readermode - Fixed Windows paths with
\u-prefixed segments (likeC:\Users\unicorn) being corrupted into CJK characters in tool inputs, which made those files inaccessible - Fixed the left arrow key discarding the conversation with no undo: presses right after editing now ask to confirm, and Esc in the agent view returns to the conversation it backgrounded
- Added HTTP status and error text to
claude mcp listand/mcpwhen a server fails to connect, and a warning for MCP config values with hidden leading or trailing whitespace - Fixed multi-line paste collapsing into one line with
jin place of newlines in terminals that encode pasted newlines as Ctrl+J - Fixed
/contextreporting stale pre-compact token usage after compacting from the message picker - Fixed
/ultrareviewfailing on descriptive arguments like "review my auth changes" — they now run a review of your current branch with the text applied as a note to the findings - Fixed
/code-review ultrasilently running a local review in non-interactive sessions — it now launches the cloud review - Fixed gateway spend metering to price Bedrock application-inference-profile ARNs and other config-mapped upstream model IDs at the configured model's rates
- Fixed mojibake when a long IDE selection was truncated mid-emoji, and a case where a tool executor error could be silently dropped
- Fixed an engine teardown race that could start and abandon a phantom turn, and made input pushed after close consistently rejected
- Fixed spurious "[Request interrupted by user]" messages after interrupted tool calls, and an unpaired
tool_useblock left in the transcript when a tool aborted mid-response - Fixed VoiceOver reading "new line" instead of echoing the typed space at the end of the input in
--ax-screen-readermode - Fixed plugin and settings panels not moving the terminal cursor to the focused row, so screen readers and magnifiers can follow arrow-key navigation
- Fixed crashes (maximum call stack exceeded) when a deeply nested watched directory tree was deleted or moved, and when rendering deeply nested UI trees
- Fixed pull request events occasionally being lost when a session exited immediately after creating or linking a PR
- Fixed the Bedrock setup wizard failing profile verification for assume-role profiles in partitioned AWS regions and on proxy-only networks
- Fixed rare negative or incorrect turn duration measurements after a system clock adjustment by timing turns with a monotonic clock
- Fixed the "N MCP servers need authentication" startup notice over-counting claude.ai connectors that aren't connected in claude.ai
- Fixed prompt history entries being dropped or duplicated when history writes raced or failed
- Fixed a retry loop that re-sent identical doomed requests after a context-overflow error with a large thinking budget;
Ctrl+Bbackgrounding now applies the same background-shell caps as other paths - Fixed agent frontmatter hooks running from untrusted folders: hooks now require the agent file's own folder to have accepted workspace trust
- Fixed fork-session lineage being lost after compaction in headless and SDK sessions
- Fixed a resumed session failing every turn, or crashing on resume, when its history held a malformed delta attachment
- Improved
/ultrareviewerror feedback so Claude can correct an invalid argument instead of retrying it unchanged - Improved auto mode: the dangerous-rm, background-
&, and suspicious-Windows-path checks no longer open permission dialogs; the auto-mode classifier adjudicates them instead - Improved sandbox command restrictions for IDE interactions
- Improved trust dialogs to name the repository root the grant covers
- Changed
/deep-researchto start only when invoked manually; Claude no longer launches it on its own - Changed plan mode with auto to no longer prompt for Bash commands the static analyzer can't prove read-only; the auto-mode classifier judges them instead
- Added an announcement when fast mode changes as a result of switching models via
/config model=<x>or Remote Control - Changed server-managed settings so benign feature and cost toggles no longer trigger the settings-approval prompt
- Changed agent markdown files to reject agent names containing
:, which is reserved for plugin namespacing - Changed skills with
context: forkto run in the background by default; opt out per skill withbackground: false - Added
yes/no/on/off/1/0(case-insensitive) as accepted values for skill and plugin frontmatter booleans, alongsidetrue/false - Fixed remote sessions continuing to send heartbeats after their worker was replaced, which left long-lived desktop and IDE processes retrying a rejected request every few seconds forever
Added
- Add emoji shortcode autocomplete in the prompt input to insert emojis by typing shortcodes like `:heart:` for ❤️, with suggestions available and disable option via `emojiCompletionEnabled` setting
- Add warnings when transcript writes are failing (e.g. disk full) or when session saving is off due to an inherited environment variable
- Add a cap on concurrently-running subagents with a default of 20, configurable via `CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS`
Changed
- Change the login-expiry warning to appear 3 days before expiry instead of 5
- Change the frontend-design plugin suggestion tip to cap at 3 lifetime impressions instead of repeating indefinitely
- Change subagents to no longer spawn nested subagents by default, with `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` allowing deeper nesting
- Improve footer PR badge links to be clickable hyperlinks even when terminal support can't be detected, with `FORCE_HYPERLINK=0` to opt out
Fixed
- Fix a memory leak where truncated MCP tool outputs kept the full untruncated result in memory for the rest of the session
- Fix Windows auto-update failures that could leave `claude.exe` missing by automatically restoring the preserved executable on failed updates
- Fix background session isolation not canonicalizing symlinked working directories, which could let sessions escape their workspace folder
- Fix auto-compact never triggering for Claude Opus 4.8 on Bedrock and `/compact` failing once over the limit
- Fix corporate mTLS, TLS-verify, OAuth scope, and proxy settings being ignored in Claude Desktop sessions
- Fix screen reader mode's startup announcement being cut off by the first prompt render
- Fix the thinking status row re-rendering every few seconds to update elapsed time and token counts
- Fix managed settings that set `OTEL_EXPORTER_OTLP_ENDPOINT` not governing all signals, with lower-scope signal-specific overrides no longer redirecting telemetry away from the managed endpoint
- Fix `--resume`/`--continue` and `/resume` failing with a TypeError when a transcript has a malformed attachment entry
- Fix Remote Control sessions not showing a pending permission prompt or dialog to viewers that connected after it appeared
- Fix background shells sometimes becoming impossible to stop after a session is sent to the background or when the session exits on a heavily loaded machine
- Fix `CLAUDE.md` or `SKILL.md` paths frontmatter value with many brace groups OOM-killing or stalling the CLI at startup by budget-bounding brace expansion
- Fix the transcript preview sitting flush against the input area when attaching to a starting background session by leaving the same one-line gap as the live layout
- Fix `--max-budget-usd` not stopping background subagents by denying new spawns and halting running background agents once the cap is reached
What's changed
- Added emoji shortcode autocomplete in the prompt input: type
:heart:to insert ❤️, or:heafor suggestions — disable with theemojiCompletionEnabledsetting - Added warnings when transcript writes are failing (e.g. disk full) or when session saving is off due to an inherited environment variable, instead of losing transcripts silently
- Fixed a memory leak where truncated MCP tool outputs kept the full untruncated result in memory for the rest of the session
- Fixed Windows auto-update failures that could leave
claude.exemissing; failed updates now restore the preserved executable automatically - Fixed background session isolation not canonicalizing symlinked working directories, which could let sessions escape their workspace folder
- Fixed auto-compact never triggering for Claude Opus 4.8 on Bedrock and
/compactfailing once over the limit - Fixed corporate mTLS, TLS-verify, OAuth scope, and proxy settings being ignored in Claude Desktop sessions
- Fixed screen reader mode's startup announcement being cut off by the first prompt render, and the thinking status row re-rendering every few seconds to update elapsed time and token counts
- Fixed managed settings that set
OTEL_EXPORTER_OTLP_ENDPOINTnot governing all signals — lower-scope signal-specific overrides no longer redirect telemetry away from the managed endpoint - Fixed
--resume/--continueand/resumefailing with a TypeError when a transcript has a malformed attachment entry - Fixed Remote Control sessions not showing a pending permission prompt or dialog to viewers that connected after it appeared
- Fixed background shells sometimes becoming impossible to stop after a session is sent to the background (
/backgroundor←) or when the session exits on a heavily loaded machine, most visible on Windows - Fixed a
CLAUDE.mdorSKILL.mdpaths frontmatter value with many brace groups OOM-killing or stalling the CLI at startup — brace expansion is now budget-bounded - Fixed the transcript preview sitting flush against the input area when attaching to a starting background session; it now leaves the same one-line gap as the live layout, so the transcript no longer shifts when the session takes over
- Improved footer PR badge links to be clickable hyperlinks even when terminal support can't be detected (e.g. over ssh/tmux); set
FORCE_HYPERLINK=0to opt out - Changed the login-expiry warning to appear 3 days before expiry instead of 5
- Capped the frontend-design plugin suggestion tip at 3 lifetime impressions instead of repeating indefinitely
- Added a cap on concurrently-running subagents (default 20, override with
CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS) so one message can't fan out unbounded background agents - Changed subagents to no longer spawn nested subagents by default; set
CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTHto allow deeper nesting - Fixed
--max-budget-usdnot stopping background subagents: once the cap is reached, new spawns are denied and running background agents are halted
Added
- Added sandbox.filesystem.disabled setting to skip filesystem isolation while keeping network egress control
Fixed
- Fixed a slowdown in long sessions where message normalization cost grew quadratically with the number of turns, causing multi-second stalls and slow resumes
- Fixed auto mode denying commands with HTTP 401 classifier errors after the OAuth token expired or rotated mid-session
- Fixed AskUserQuestion telling Claude to continue even when your answer asked it to wait or explain first — free-text answers now get neutral wording
- Fixed Claude Code on the web re-asking the same question and dropping your answer after the session sat idle for a few minutes
- Fixed @-mentions silently attaching nothing after file-modifying hooks, vim dot-repeat of c-operators and paste, statusline running twice on resume, and resume-picker hangs on failure
- Fixed resumed background agent sessions reverting to the default agent: the agent's prompt and tool restrictions are now restored
- Fixed worktree-isolated subagents redirecting git into the shared checkout via git -C, --git-dir, or GIT_DIR/GIT_WORK_TREE
- Fixed worktree sessions landing in another project's leftover worktree when the working directory did not match the selected project
- Fixed background sessions whose worktree has no git repository being undeletable
- Fixed claude daemon stop --any potentially terminating an unrelated process via a stale legacy daemon lockfile
- Fixed Esc-Esc at an idle prompt not opening the rewind picker in long-running sessions with background tasks
- Fixed Bash command permission checking for compound statements with redirects inside && lists or negations
- Fixed pressing Ctrl+X twice in the agent list failing to delete a session, and deleted sessions reappearing when their background worker had died
- Fixed background subagents getting cancelled when a high-priority message arrives during their startup window
- Fixed mouse and focus garbage in the terminal while a GUI editor from /memory, /plan, /keybindings, or Ctrl+G is open; /memory no longer waits for the editor to close
- Fixed Claude-in-Chrome 403-looping on reconnect when the session's OAuth token lacks a required scope
- Fixed workflow saves and scheduled-task writes following a symlink at .claude, which could redirect writes outside the project
- Fixed MCP re-authenticate revoking working credentials before the new sign-in succeeds, and the reconnect needs-auth message in background sessions pointing at an unusable command
- Fixed read-only commands on Windows accessing network paths without a permission prompt
What's changed
- Added
sandbox.filesystem.disabledsetting to skip filesystem isolation while keeping network egress control - Fixed a slowdown in long sessions where message normalization cost grew quadratically with the number of turns, causing multi-second stalls and slow resumes
- Fixed auto mode denying commands with "HTTP 401" classifier errors after the OAuth token expired or rotated mid-session
- Fixed AskUserQuestion telling Claude to continue even when your answer asked it to wait or explain first — free-text answers now get neutral wording
- Fixed Claude Code on the web re-asking the same question and dropping your answer after the session sat idle for a few minutes
- Fixed @-mentions silently attaching nothing after file-modifying hooks, vim dot-repeat of
c-operators and paste, statusline running twice on resume, and resume-picker hangs on failure - Fixed resumed background agent sessions reverting to the default agent: the agent's prompt and tool restrictions are now restored
- Fixed worktree-isolated subagents redirecting git into the shared checkout via
git -C,--git-dir, orGIT_DIR/GIT_WORK_TREE - Fixed worktree sessions landing in another project's leftover worktree when the working directory did not match the selected project
- Fixed background sessions whose worktree has no git repository being undeletable
- Fixed
claude daemon stop --anypotentially terminating an unrelated process via a stale legacy daemon lockfile - Fixed Esc-Esc at an idle prompt not opening the rewind picker in long-running sessions with background tasks
- Fixed Bash command permission checking for compound statements with redirects inside
&&lists or negations - Fixed pressing Ctrl+X twice in the agent list failing to delete a session, and deleted sessions reappearing when their background worker had died
- Fixed background subagents getting cancelled when a high-priority message arrives during their startup window
- Fixed mouse and focus garbage in the terminal while a GUI editor from
/memory,/plan,/keybindings, or Ctrl+G is open;/memoryno longer waits for the editor to close - Fixed Claude-in-Chrome 403-looping on reconnect when the session's OAuth token lacks a required scope
- Fixed workflow saves and scheduled-task writes following a symlink at
.claude, which could redirect writes outside the project - Fixed MCP re-authenticate revoking working credentials before the new sign-in succeeds, and the reconnect needs-auth message in background sessions pointing at an unusable command
- Fixed read-only commands on Windows accessing network paths without a permission prompt
- Fixed Bash command parsing of non-ASCII characters to match real shell word boundaries
- Fixed PowerShell tool permission validation of commands containing invisible Unicode characters
- Fixed dialogs in fullscreen mode stretching past the right-hand edge of their panel
- Fixed the
/configsettings list in fullscreen mode clipping its keyboard-hint footer - Fixed the transcript-mode (Ctrl+O) footer hint wrapping on terminals narrower than 104 columns
- Fixed the Prometheus metrics endpoint (
OTEL_METRICS_EXPORTER=prometheus) emitting invalid# UNITlines - Fixed skills and commands changed during a session not appearing in the slash menu until restart
- Fixed plugin skills with a
namefrontmatter field losing their plugin prefix in slash-command autocomplete - Fixed telemetry misreporting permission denials: failed permission-prompt requests no longer count as user rejections, and user interrupts are now reported as user aborts instead of rejections
- Improved the
/forkconfirmation to one line with the new session's name,claude attachid, and a note when the copy shares your checkout - Improved validation of
gitandghcommand arguments in the PowerShell tool - Improved the
/ultrareviewdiff-too-large error to show configured limits, measured diff size, and largest contributing files - Improved
/code-review ultraempty-diff message to name the exact base ref and suggest passing an explicit base - Improved the spend limit adjustment prompt to show the server's reason when a spend limit change is rejected
/contextnow shows an explicit warning when the conversation exceeds the context window, and a failed/compactdisplays as an error/rewindno longer restores or deletes files through symlinks or hard links at tracked paths and reports how many paths it skipped- Background sessions:
/mcpand/install-github-appnow park a "needs input" request in the agent view when no client is attached - Updated the bundled dataviz skill: reordered the default chart palette and fixed guidance that suggested direct labels for four-series charts
- [VSCode] Fixed right-to-left text (Arabic, Hebrew, Persian) rendering in the wrong order when mixed with English or code
- Fixed cloud sessions dropping the in-flight message when the session's container restarts mid-turn — the interrupted turn now re-runs on resume instead of leaving the session unresponsive
Changed
- Claude no longer runs the /verify and /code-review skills automatically; they must be invoked with /verify or /code-review when needed
What's changed
- Claude no longer runs the
/verifyand/code-reviewskills on its own; invoke them with/verifyor/code-reviewwhen you want them
Added
- Added the EndConversation tool: Claude can end sessions with highly abusive users or jailbreak attempts
- Added a periodic progress heartbeat for long-running tool calls that previously went silent
- Added an ISO `modified` timestamp to memory file frontmatter
- Added `message.uuid`, `client_request_id`, and `tool_source` attributes to OpenTelemetry log events for message-level correlation and tool provenance
- Added `CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH` to configure the 60 KB truncation limit on OpenTelemetry content attributes
- Added reasoning effort to the `subagentStatusLine` payload, so custom agent rows can render model and effort
- Added permission prompts for `docker` commands carrying daemon-redirect flags (`--url`, `--connection`, `--identity`, and Podman's remote mode) that previously ran without one
Fixed
- Fixed single-segment `dir/**` allow rules like `Edit(src/**)` auto-approving writes to nested `dir/` directories anywhere in the tree instead of only `<cwd>/dir`
- Fixed a permission-check bypass affecting commands run in Windows PowerShell 5.1 sessions
- Fixed Bash permission checks to fail closed on file-descriptor redirect forms that bash parses differently than the permission analyzer
- Fixed Bash permission checks misjudging very long commands — commands over 10,000 characters now always prompt instead of running automatically
- Fixed Bash permission checks treating zsh variable subscripts and modifiers in `[[ ]]` comparisons as inert text — these commands now prompt for approval
- Fixed Bash permission checks to no longer auto-approve certain `help` and `man` commands that could run unsafe options, command substitutions, or backslash paths
- Fixed permission prompts on remote sessions that could proceed before the local confirmation dialog
- Fixed a crash when a GrowthBook feature evaluates to null, and a bug where a malformed flag payload could wipe the cached feature flags
- Fixed Bash tool killing the Claude session when a `pkill -f` pattern accidentally matched the CLI's own process (Linux)
- Fixed unbounded memory growth when `--settings` points at a device file or multi-GB file; oversized (>2 MiB) settings files now fail at startup with a clear error
- Fixed streaming turns failing with "Socket is closed" behind corporate proxies on Windows
- Fixed stream-json output truncation at exit for slow-reading SDK/pipeline consumers; the exit drain now scales with queued bytes instead of a flat 2s cap
- Fixed scheduled tasks refusing their own configured prompt as untrusted input — the fired prompt is now delivered as the session's assigned task
What's changed
- Fixed single-segment
dir/**allow rules likeEdit(src/**)auto-approving writes to nesteddir/directories anywhere in the tree instead of only<cwd>/dir - Fixed a permission-check bypass affecting commands run in Windows PowerShell 5.1 sessions
- Fixed Bash permission checks to fail closed on file-descriptor redirect forms that bash parses differently than the permission analyzer
- Fixed Bash permission checks misjudging very long commands — commands over 10,000 characters now always prompt instead of running automatically
- Fixed Bash permission checks treating zsh variable subscripts and modifiers in
[[ ]]comparisons as inert text — these commands now prompt for approval - Fixed Bash permission checks to no longer auto-approve certain
helpandmancommands that could run unsafe options, command substitutions, or backslash paths - Fixed permission prompts on remote sessions that could proceed before the local confirmation dialog
- Added the EndConversation tool: Claude can end sessions with highly abusive users or jailbreak attempts, as on claude.ai since 2025 — see https://www.anthropic.com/research/end-subset-conversations
- Added a periodic progress heartbeat for long-running tool calls that previously went silent
- Added an ISO
modifiedtimestamp to memory file frontmatter - Added
message.uuid,client_request_id, andtool_sourceattributes to OpenTelemetry log events for message-level correlation and tool provenance - Added
CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTHto configure the 60 KB truncation limit on OpenTelemetry content attributes - Added reasoning effort to the
subagentStatusLinepayload, so custom agent rows can render model and effort - Added permission prompts for
dockercommands (including the Podmandockershim) carrying daemon-redirect flags (--url,--connection,--identity, and Podman's remote mode) that previously ran without one - Fixed a crash when a GrowthBook feature evaluates to null, and a bug where a malformed flag payload could wipe the cached feature flags
- Fixed Bash tool killing the Claude session when a
pkill -fpattern accidentally matched the CLI's own process (Linux) - Fixed unbounded memory growth when
--settingspoints at a device file or multi-GB file; oversized (>2 MiB) settings files now fail at startup with a clear error - Fixed streaming turns failing with "Socket is closed" behind corporate proxies on Windows
- Fixed stream-json output truncation at exit for slow-reading SDK/pipeline consumers; the exit drain now scales with queued bytes instead of a flat 2s cap
- Fixed scheduled tasks refusing their own configured prompt as untrusted input — the fired prompt is now delivered as the session's assigned task
- Fixed PowerShell tool commands hanging until timeout when a child process waited on standard input (Windows)
- Fixed Python scripts under the PowerShell tool crashing with UnicodeDecodeError when reading non-UTF-8 data from standard input (Windows)
- Fixed Python scripts run via the PowerShell tool crashing with UnicodeEncodeError on non-ASCII output, and PowerShell 7 error messages containing raw ANSI escape sequences (Windows)
- Fixed the PowerShell tool reporting
where.exe,fc.exe, anddiff.exeas errors when they return a valid negative answer (Windows) - Fixed
>and>>under the PowerShell tool on Windows PowerShell 5.1 writing UTF-16LE files that other tools couldn't read as UTF-8 - Fixed a displaced background daemon deleting its successor's control socket on shutdown, which made the next client kill the healthy replacement daemon
- Fixed background sessions parked with
←or/backgroundand left idle keeping the background daemon and a worker process alive indefinitely - Fixed completed background sessions being impossible to remove via
claude rmor the agent view once the background service had gone idle - Fixed background sessions dispatched from a non-git folder being impossible to delete from the agents view
- Fixed reopening a stopped background session failing to restore its saved conversation when an unreadable folder exists in the session store
- Fixed the Remote Control "session ready" push notification firing for sessions where Remote Control was not explicitly enabled
- Fixed
/install-github-appand the/mcpsettings menu being blocked in agent-view sessions — they're now refused only in background sessions with no terminal attached - Fixed plugins enabled via the
--settingsCLI flag not loading (regression since v2.1.181) - Fixed feature flags going stale in long-running sessions after the OAuth token rotates
- Fixed
/ultrareviewrefusing to run in repos with no merge base — it now offers to review all tracked files - Fixed
claude updateandclaude doctorhanging silently, and the/statusSystem diagnostics section going blank, when a shell-config path is a directory - Fixed memory frontmatter values being silently truncated at an inline
#when memory files are saved - Fixed session cost and token telemetry double-counting on streams that emit multiple cumulative
message_deltaframes - Fixed a spurious "check your network" warning that appeared while the advisor was thinking
- Fixed hooks with exit code 2 not blocking as documented when the hook's stdout JSON fails schema validation
- Fixed OTel log events emitted outside the turn's async context missing the interaction span's trace context
- Fixed MCP transient errors during prompts/resources refresh clearing the server's slash commands and resources
- Improved the
claude rcworkspace-trust error in the home directory to say trust there is never saved and to suggest running from a project directory - Changed single-segment
dir/**hookif:conditions to match only<cwd>/dir; write**/dir/**for any-depth matching.deny/askpermission rules keep their any-depth match. - Changed
filecommands using-m/--magic-fileor-f/--files-fromto require permission instead of being auto-allowed as read-only - Changed keep-alive connection pooling to disable after a stale-connection error, so retries open a fresh socket
- Changed SessionStart hooks to report source
"fork"when a session begins as a fork instead of"resume"
Added
- Added claude auto-mode reset to restore the default auto-mode configuration, with a confirmation prompt
- Added a session-wide limit on WebSearch tool calls (default 200, tunable via CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION)
- Added a per-session cap on subagent spawns (default 200, override with CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION)
- MCP tool calls running longer than 2 minutes now move to the background automatically so the session stays usable
- Typing /resume in the agent view now opens a picker of past sessions and resumes your pick as a background session
Changed
- /fork now copies your conversation into a new background session while you keep working; the in-session subagent it used to launch is now /subtask
Fixed
- Fixed plan mode auto-running file-modifying Bash commands without a permission prompt
- Fixed worktree creation following a repository-committed symlink at .claude/worktrees, which could create files outside the repository
- Fixed a continue:false hook's halt being dropped when the tool fails or completes mid-stream
- Fixed SIGTERM during a running Bash tool orphaning the command's process tree in print/SDK mode
- Fixed /background and claude --bg failing with EUNKNOWN on Windows when Group Policy blocks PowerShell 5.1
- Fixed shell mode (!) not executing commands containing file paths while the path autocomplete popup was open
- Fixed auto-mode denial notifications rendering broken characters when a long denial reason was truncated mid-emoji
- Fixed Ctrl+J not inserting a newline in the agent view dispatch input on terminals with extended key reporting
- Fixed /ultrareview rejecting PR references like #123, PR 123, and pasted PR URLs
- Fixed /ultrareview <branch> not fetching the branch from origin when it exists remotely
- Fixed /ultrareview skipping the billing confirmation in a new conversation after /clear
- Fixed /ultrareview's not a git repository error on Claude Desktop to suggest the project's repository folder
- Fixed hosted sessions failing at startup when repository settings configured mTLS certs, extra CA bundles, or OAuth scopes
- Fixed a spurious File has not been read yet error when editing a file that had been read with offset/limit before resuming a session
What's changed
/forknow copies your conversation into a new background session (its own row inclaude agents) while you keep working; the in-session subagent it used to launch is now/subtask- Added
claude auto-mode resetto restore the default auto-mode configuration, with a confirmation prompt (pass--yesto skip) - Added a session-wide limit on WebSearch tool calls (default 200, tunable via
CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION) to stop runaway search loops - Added a per-session cap on subagent spawns (default 200, override with
CLAUDE_CODE_MAX_SUBAGENTS_PER_SESSION) to stop runaway delegation loops;/clearresets the budget - MCP tool calls running longer than 2 minutes now move to the background automatically so the session stays usable; configure the threshold or disable with
CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS - Typing
/resumein the agent view now opens a picker of past sessions — including sessions deleted from the list — and resumes your pick as a background session - Fixed plan mode auto-running file-modifying Bash commands (e.g.
touch,rm) without a permission prompt or SDKcanUseToolcallback - Fixed worktree creation following a repository-committed symlink at
.claude/worktrees, which could create files outside the repository - Fixed a
continue:falsehook's halt being dropped when the tool fails or completes mid-stream, and hook infrastructure errors being misreported as user rejections - Fixed SIGTERM during a running Bash tool orphaning the command's process tree in print/SDK mode; the CLI now aborts the turn, kills the tree, and exits 143
- Fixed
/backgroundandclaude --bgfailing with "EUNKNOWN: unknown error, uv_spawn" on Windows when Group Policy blocks PowerShell 5.1; the daemon now prefers PowerShell 7 - Fixed shell mode (
!) not executing commands containing file paths while the path autocomplete popup was open - Fixed auto-mode denial notifications rendering broken characters when a long denial reason was truncated mid-emoji
- Fixed Ctrl+J not inserting a newline in the agent view dispatch input on terminals with extended key reporting, and surfaced the newline shortcut in the
?help overlay - Fixed
/ultrareviewrejecting PR references like#123,PR 123, and pasted PR URLs; error hints now name the command you actually typed - Fixed
/ultrareview <branch>not fetching the branch from origin when it exists remotely; it now suggests the closest branch name on typos - Fixed
/ultrareviewskipping the billing confirmation in a new conversation after/clear - Fixed
/ultrareview's "not a git repository" error on Claude Desktop now suggesting the project's repository folder instead of terminal commands - Fixed hosted (host-managed) sessions failing at startup when repository settings configured mTLS certs, extra CA bundles, or OAuth scopes; these transport settings are now ignored with a warning
- Fixed a spurious "File has not been read yet" error when editing a file that had been read with offset/limit before resuming a session
- Fixed
ExitWorktreefailing with "no active EnterWorktree session" after resuming a session with--continue/--resumein print/SDK mode - Fixed the workflow agent grid staying empty for Remote Control clients that join a session mid-run
- Fixed streaming-mode control requests being marked complete before their handler finished, which could lose the request on session restart
- Fixed background sessions created with
/forklosing their live-parent protection after a state write failure - Fixed reopening a stopped background session from the agent view failing silently — it now resumes the session, or shows why it can't and lets you force a restart
- Fixed agent teams: a stopping teammate could send the leader duplicate idle notifications when team initialization re-ran within a session
- Fixed the plan-approval dialog footer splitting "ctrl+g to edit in " apart when the file path is long
- Fixed the welcome banner keeping its old panel widths after a combined width+height terminal resize in fullscreen mode
- Fixed diff previews losing their line numbers and +/- markers in narrow layouts
- Fixed @-mentions attaching nothing after a partial file read, plugin uninstall targeting the wrong marketplace, and false "Command timed out" on exit code 143
- Fixed OpenTelemetry HTTP exports being rejected with 411/400 by Azure Monitor and other endpoints that don't accept chunked transfer encoding
- Fixed OTLP event log records missing
trace_id/span_idwhenTRACEPARENTis set in SDK/headless mode - Fixed conversations with many images incorrectly failing with "Request too large" errors, and improved the error message to explain the actual cause
- Fixed web search and web fetch returning "API Error" text as search results or page content when the API was overloaded
- Improved web search and web fetch reliability by retrying 529 errors and rate-limited requests with bounded backoff
- Improved prompt caching: the mid-conversation system block now works behind LLM gateways and custom base URLs (Bedrock, Vertex, 1P)
- Improved background agent attach: cold-attaching now instantly shows the formatted transcript while the session boots, instead of a blank wait
- Reduced token usage in inter-agent messaging:
SendMessagebodies are no longer duplicated into replayed history and tool results - Changed
/forkto name the copy after your prompt when the session has no title, so the row is recognizable in the agent view - Changed bare
/btwto reopen the side-question panel on your most recent exchange so you can browse earlier answers - Changed the
←footer hint to pulseN donefor a moment when a background agent finishes while nothing needs your input - Deprecated the Task tool's
modeparameter (now ignored); subagents inherit the parent session's permission mode by default - Changed Enterprise
forceLoginMethodto be enforced for VS Code extension, SDK,setup-token, andinstall-github-applogins, not just the terminal - Changed session transcripts to record the reasoning effort level on each assistant message
- Changed headless/SDK sessions to apply a
set_modelcontrol request mid-turn; the next model round-trip uses the new model instead of waiting for the next turn - Changed agent view /
claude agents --json: sessions waiting on a sandbox, MCP-input, or managed-settings prompt now show as "Needs input" instead of "Working" - Updated the auth status panel title from "Cloud authentication" to "Authentication"
- Corrected an earlier release note (2.1.200): tmux through the 3.6 series lacks synchronized output; newer tmux with support is detected automatically
Added
- Add `--forward-subagent-text` flag and `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT` environment variable to include subagent text and thinking in stream-json output
Fixed
- Fix permission previews relayed to chat channels not neutralizing bidirectional-override, zero-width, and look-alike quote characters so tool inputs cannot visually alter the approval message
- Fix auto mode overriding a PreToolUse hook's `ask` decision for unsandboxed Bash — hook `ask` now floors the decision at a prompt
- Fix parallel Claude Code sessions all logging out simultaneously after wake-from-sleep when many sessions share one credential store
- Fix plugin MCP servers not reconnecting after an idle web session woke, leaving MCP calls failing until the next message
- Fix Claude Code on Vertex and Bedrock attempting the default Opus model at startup and printing a spurious fallback notice when a model is explicitly configured
- Fix subagents spawned with an explicit model override reverting to the parent's model when resumed or sent a follow-up message
- Fix nested `.claude/rules/*.md` files loading even when setting sources exclude project settings
- Fix file upload validation: filenames ending in a DOS device suffix (`.prn`) or trailing dot are now accepted, and files with multiple hard links are refused
- Fix file uploads to Claude in Chrome from remote and CLI sessions
- Fix edits that leave the input as "?" being silently swallowed and toggling the shortcuts panel
- Fix a startup hang when the Claude in Chrome extension is enabled but Chrome is not running
- Fix a 300ms delay revealing async content (Settings tabs, Stats, diff views, and other loading states)
- Fix reopening a just-stopped background session from the agents view starting a blank conversation under the same session id
- Fix `/loop` hiding the session from `/resume` after a single use
- Fix screen reader users losing the audible terminal bell after `/terminal-setup` or onboarding terminal setup
- Fix background jobs on LLM gateway auth coming back "Not logged in" after the daemon respawns them
- Fix `claude agents` jobs becoming permanently undeletable when git no longer recognizes their worktree — the row now shows why the delete was refused instead of silently reappearing
- Fix `/clear` not resetting the session cost counter — the statusline's cost now starts at $0 after `/clear`
What's changed
- Added
--forward-subagent-textflag andCLAUDE_CODE_FORWARD_SUBAGENT_TEXTenvironment variable to include subagent text and thinking in stream-json output - Fixed permission previews relayed to chat channels not neutralizing bidirectional-override, zero-width, and look-alike quote characters, so tool inputs cannot visually alter the approval message
- Fixed auto mode overriding a PreToolUse hook's
askdecision for unsandboxed Bash — a hookasknow floors the decision at a prompt - Fixed parallel Claude Code sessions all logging out simultaneously after wake-from-sleep when many sessions share one credential store
- Fixed plugin MCP servers not reconnecting after an idle web session woke, leaving MCP calls failing until the next message
- Fixed Claude Code on Vertex and Bedrock attempting the default Opus model at startup and printing a spurious fallback notice when a model is explicitly configured
- Fixed subagents spawned with an explicit model override reverting to the parent's model when resumed or sent a follow-up message
- Fixed nested
.claude/rules/*.mdfiles loading even when setting sources exclude project settings - Fixed file upload validation: filenames ending in a DOS device suffix (
.prn) or trailing dot are now accepted, and files with multiple hard links are refused - Fixed file uploads to Claude in Chrome from remote and CLI sessions
- Fixed edits that leave the input as "?" being silently swallowed and toggling the shortcuts panel
- Fixed a startup hang when the Claude in Chrome extension is enabled but Chrome is not running
- Fixed a 300ms delay revealing async content (Settings tabs, Stats, diff views, and other loading states)
- Fixed reopening a just-stopped background session from the agents view starting a blank conversation under the same session id
- Fixed
/loophiding the session from/resumeafter a single use - Fixed screen reader users losing the audible terminal bell after
/terminal-setupor onboarding terminal setup - Fixed background jobs on LLM gateway auth (
ANTHROPIC_AUTH_TOKEN+ANTHROPIC_BASE_URL) coming back "Not logged in" after the daemon respawns them - Fixed
claude agentsjobs becoming permanently undeletable when git no longer recognizes their worktree — the row now shows why the delete was refused instead of silently reappearing - Fixed
/clearnot resetting the session cost counter — the statusline's cost now starts at $0 after/clear - Fixed Claude in Chrome setup pages failing to open in the browser on Windows
- Fixed headless print-mode sessions on Windows crashing or silently exiting when stdin is unreadable
- Fixed background session titles in the agents view showing the naming model's refusal text when the prompt contains a link
- Fixed background agents killed by the user auto-respawning, and revived agents re-running stale prompts from old sessions
- Fixed routines with no schedule reporting a next run time in the year 1
- Hardened synced skill/plugin directory naming on Windows and kept CCR web fetch/search proxies working after
/clear - Improved terminal layout and rendering performance
- Improved background agent result reporting — Claude now reports the status of still-running agents and waits for the real completion instead of fabricating results
- Improved the memory index over-limit warning to measure only loaded content, excluding frontmatter and HTML comments
- Updated integer environment variables (timeouts, token budgets, retry counts) to accept scientific notation and digit-separator spellings like
1e6and64_000 - Updated documentation links to the current docs sites
- Changed "always allow" permission rules to save at the repository root, so approvals granted in a git worktree persist across sessions and worktrees
- Changed
/usage-creditsto ask for confirmation before sending a request to organization admins - Changed Vim mode
sandS(substitute char/line) to work in NORMAL mode, matching vim behavior - [VSCode] Updated the Remote Control banner to describe what it does
- Claude in Chrome: hardened file-upload path validation
- Claude in Chrome:
save_to_diskon screenshot actions now writes the image to disk and returns the path; previously it did nothing - Fixed a prompt-caching regression on Bedrock, Vertex, Mantle, and Foundry that billed the trailing system context block as fresh input tokens on every request.
Added
- Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck
- Added a startup warning for Write(path), NotebookEdit(path), and Glob(path) permission rules — use Edit(path) or Read(path) instead
Fixed
- Fixed isolation: 'worktree' subagents being able to run git-mutating commands against the main repo checkout instead of their own isolated worktree
- Fixed the ultracode keyword opt-in firing on non-human-originated input such as webhook payloads and relayed PR comments
- Fixed a rendered text fragment leaking into crash telemetry when a UI component returned content outside a styled text element
- Fixed paste markers leaking into external editors opened from Claude Code, which could appear as stray È/É characters around pasted text
- Fixed claude attach sometimes failing with "job not found" or "agent is still starting" errors during session transitions — attach now waits for the daemon to settle, and terminal resizes during a slow attach are applied once it completes
- Fixed a session crash when a tool's result renderer returned a numeric bigint value or plain text instead of a UI element
- Fixed a hook callback timeout being misreported to the model as a user rejection, which made unattended sessions stop and wait
- Fixed Claude assuming a cd took effect after its command was moved to the background; the tool result now states the working directory is unchanged
- Fixed plugin-provided MCP servers being torn down when MCP servers are re-synced mid-session
- Fixed plan approvals without edits being labeled "(edited by user)" and overwriting the plan file with a stale snapshot
- Fixed /doctor skipping its auto-mode-default proposal on Bedrock, Vertex, and Foundry, where auto mode no longer needs an opt-in
- Fixed Grep content mode claiming "No matches found" when paginating past the end of results
- Fixed unmatched $1/$2 positional placeholders in skills and commands being silently stripped; they are now preserved verbatim
- Fixed plugin cache writes leaving temp files behind on failure and failing on locked-file renames on Windows and network filesystems
- Fixed background workers crash-looping when a client resets its connection to the background service
- Fixed claude agents --effort ultracode not reaching dispatched sessions; the value was silently dropped
- Fixed pressing ← to open the agents view dropping the task tracker when returning to the session
- Fixed the agents dashboard retaining pasted images from abandoned reply drafts after their session was deleted
What's changed
- Added a live elapsed-time counter to the collapsed tool summary line so long-running tool calls visibly tick instead of looking stuck
- Added a startup warning for
Write(path),NotebookEdit(path), andGlob(path)permission rules — useEdit(path)orRead(path)instead - Fixed
isolation: 'worktree'subagents being able to run git-mutating commands against the main repo checkout instead of their own isolated worktree - Fixed the
ultracodekeyword opt-in firing on non-human-originated input such as webhook payloads and relayed PR comments - Fixed a rendered text fragment leaking into crash telemetry when a UI component returned content outside a styled text element
- Fixed paste markers leaking into external editors opened from Claude Code, which could appear as stray È/É characters around pasted text
- Fixed
claude attachsometimes failing with "job not found" or "agent is still starting" errors during session transitions — attach now waits for the daemon to settle, and terminal resizes during a slow attach are applied once it completes - Fixed a session crash when a tool's result renderer returned a numeric bigint value or plain text instead of a UI element
- Fixed a hook callback timeout being misreported to the model as a user rejection, which made unattended sessions stop and wait
- Fixed Claude assuming a
cdtook effect after its command was moved to the background; the tool result now states the working directory is unchanged - Fixed plugin-provided MCP servers being torn down when MCP servers are re-synced mid-session
- Fixed plan approvals without edits being labeled "(edited by user)" and overwriting the plan file with a stale snapshot
- Fixed
/doctorskipping its auto-mode-default proposal on Bedrock, Vertex, and Foundry, where auto mode no longer needs an opt-in - Fixed Grep content mode claiming "No matches found" when paginating past the end of results
- Fixed unmatched
$1/$2positional placeholders in skills and commands being silently stripped; they are now preserved verbatim - Fixed plugin cache writes leaving temp files behind on failure and failing on locked-file renames on Windows and network filesystems
- Fixed background workers crash-looping when a client resets its connection to the background service
- Fixed
claude agents --effort ultracodenot reaching dispatched sessions; the value was silently dropped - Fixed pressing ← to open the agents view dropping the task tracker when returning to the session
- Fixed the agents dashboard retaining pasted images from abandoned reply drafts after their session was deleted
- Fixed killed background sessions leaving a permanent
git worktree lockbehind; the periodic sweep now releases locks whose owning process is gone - Fixed SDK MCP servers registered via an
initializecontrol request waiting until the next turn to start connecting - Fixed returning to the agents view from a session leaving overlapping ghost frames with
CLAUDE_CODE_DISABLE_ALTERNATE_SCREEN=1 - Fixed late-appearing
.claude/*symlinks not being reconciled into the sandbox deny-write list - Hardened the Agent tool against indirect prompt injection via content a subagent read
- Improved the Bash/PowerShell tool message when a command hits its timeout and is auto-backgrounded, so the model can distinguish a hang from an explicit background request
- Improved auto mode: the permission classifier now defaults to Sonnet 5 for external sessions, validated on the session's first request and pinned for the session
- Improved the bundled dataviz skill's chart color validation with perceptual OKLab color difference and recalibrated color-blindness thresholds
- Memory writes that leave a MEMORY.md index over its read limit now produce an explicit error instead of silent truncation
- Screen reader mode now announces permission mode changes aloud when cycling modes with Shift+Tab
- The agents footer hint now shows how many background agents are waiting on your input, with a brief color emphasis when the count changes
- Agent view: the session you pressed ← from stays visibly marked even after mouse hover or arrow keys move the selection
- Fable temporarily shows as unavailable in the advisor picker while a server-side issue causing Fable advisor failures is fixed